| { | |
| "best_metric": 0.4414389729499817, | |
| "best_model_checkpoint": "autotrain-5fp4q-xo5q8/checkpoint-52", | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 52, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.038461538461538464, | |
| "grad_norm": 22.706926345825195, | |
| "learning_rate": 6.25e-06, | |
| "loss": 1.7992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07692307692307693, | |
| "grad_norm": 14.82021427154541, | |
| "learning_rate": 1.25e-05, | |
| "loss": 1.6176, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11538461538461539, | |
| "grad_norm": 21.29955291748047, | |
| "learning_rate": 1.8750000000000002e-05, | |
| "loss": 1.6712, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 10.56375503540039, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1576, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19230769230769232, | |
| "grad_norm": 12.371294021606445, | |
| "learning_rate": 3.125e-05, | |
| "loss": 1.1625, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23076923076923078, | |
| "grad_norm": 10.228344917297363, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.9789, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2692307692307692, | |
| "grad_norm": 7.665449619293213, | |
| "learning_rate": 4.375e-05, | |
| "loss": 0.6949, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 4.8355607986450195, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3715, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.34615384615384615, | |
| "grad_norm": 3.644941806793213, | |
| "learning_rate": 4.928571428571429e-05, | |
| "loss": 0.2734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 10.93883228302002, | |
| "learning_rate": 4.8571428571428576e-05, | |
| "loss": 1.1038, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4230769230769231, | |
| "grad_norm": 1.8329538106918335, | |
| "learning_rate": 4.785714285714286e-05, | |
| "loss": 0.0594, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.46153846153846156, | |
| "grad_norm": 6.308378219604492, | |
| "learning_rate": 4.714285714285714e-05, | |
| "loss": 0.5268, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 11.916308403015137, | |
| "learning_rate": 4.642857142857143e-05, | |
| "loss": 1.3736, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5384615384615384, | |
| "grad_norm": 7.456629276275635, | |
| "learning_rate": 4.5714285714285716e-05, | |
| "loss": 1.0286, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5769230769230769, | |
| "grad_norm": 8.702776908874512, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.7341, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 13.713752746582031, | |
| "learning_rate": 4.428571428571428e-05, | |
| "loss": 1.0677, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.6538461538461539, | |
| "grad_norm": 9.722982406616211, | |
| "learning_rate": 4.3571428571428576e-05, | |
| "loss": 0.9429, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.6923076923076923, | |
| "grad_norm": 4.836060523986816, | |
| "learning_rate": 4.2857142857142856e-05, | |
| "loss": 0.4127, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7307692307692307, | |
| "grad_norm": 5.4703497886657715, | |
| "learning_rate": 4.214285714285714e-05, | |
| "loss": 0.4774, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 3.5811495780944824, | |
| "learning_rate": 4.1428571428571437e-05, | |
| "loss": 0.4939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8076923076923077, | |
| "grad_norm": 7.475313186645508, | |
| "learning_rate": 4.0714285714285717e-05, | |
| "loss": 0.8256, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 5.056193828582764, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5561, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.8846153846153846, | |
| "grad_norm": 3.139153242111206, | |
| "learning_rate": 3.928571428571429e-05, | |
| "loss": 0.2875, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 7.5760884284973145, | |
| "learning_rate": 3.857142857142858e-05, | |
| "loss": 0.5746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9615384615384616, | |
| "grad_norm": 7.418881893157959, | |
| "learning_rate": 3.785714285714286e-05, | |
| "loss": 0.7306, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 8.691544532775879, | |
| "learning_rate": 3.7142857142857143e-05, | |
| "loss": 0.2932, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8627450980392157, | |
| "eval_f1_macro": 0.7521367521367521, | |
| "eval_f1_micro": 0.8627450980392157, | |
| "eval_f1_weighted": 0.8526897938662645, | |
| "eval_loss": 0.4614105522632599, | |
| "eval_precision_macro": 0.8204607046070461, | |
| "eval_precision_micro": 0.8627450980392157, | |
| "eval_precision_weighted": 0.8576040172166427, | |
| "eval_recall_macro": 0.7095095095095095, | |
| "eval_recall_micro": 0.8627450980392157, | |
| "eval_recall_weighted": 0.8627450980392157, | |
| "eval_runtime": 42.7222, | |
| "eval_samples_per_second": 1.194, | |
| "eval_steps_per_second": 0.094, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0384615384615385, | |
| "grad_norm": 5.2084550857543945, | |
| "learning_rate": 3.642857142857143e-05, | |
| "loss": 0.4819, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.0769230769230769, | |
| "grad_norm": 5.608432292938232, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.5022, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.1153846153846154, | |
| "grad_norm": 2.5721189975738525, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.2137, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1538461538461537, | |
| "grad_norm": 3.4027936458587646, | |
| "learning_rate": 3.428571428571429e-05, | |
| "loss": 0.2027, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1923076923076923, | |
| "grad_norm": 6.340023517608643, | |
| "learning_rate": 3.357142857142857e-05, | |
| "loss": 0.4467, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2307692307692308, | |
| "grad_norm": 4.974024295806885, | |
| "learning_rate": 3.285714285714286e-05, | |
| "loss": 0.3403, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.2692307692307692, | |
| "grad_norm": 0.9552409052848816, | |
| "learning_rate": 3.2142857142857144e-05, | |
| "loss": 0.0516, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.3076923076923077, | |
| "grad_norm": 2.218487024307251, | |
| "learning_rate": 3.142857142857143e-05, | |
| "loss": 0.1517, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.3461538461538463, | |
| "grad_norm": 4.473520278930664, | |
| "learning_rate": 3.071428571428572e-05, | |
| "loss": 0.2437, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.3846153846153846, | |
| "grad_norm": 0.7838555574417114, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0439, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4230769230769231, | |
| "grad_norm": 5.70513391494751, | |
| "learning_rate": 2.9285714285714288e-05, | |
| "loss": 0.4307, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.4615384615384617, | |
| "grad_norm": 6.128334999084473, | |
| "learning_rate": 2.857142857142857e-05, | |
| "loss": 0.3735, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 3.746047019958496, | |
| "learning_rate": 2.785714285714286e-05, | |
| "loss": 0.2421, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5384615384615383, | |
| "grad_norm": 9.368988990783691, | |
| "learning_rate": 2.714285714285714e-05, | |
| "loss": 1.0537, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5769230769230769, | |
| "grad_norm": 4.9520087242126465, | |
| "learning_rate": 2.642857142857143e-05, | |
| "loss": 0.4067, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6153846153846154, | |
| "grad_norm": 5.346065044403076, | |
| "learning_rate": 2.5714285714285714e-05, | |
| "loss": 0.3763, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6538461538461537, | |
| "grad_norm": 4.066850185394287, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.2232, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 0.366755872964859, | |
| "learning_rate": 2.4285714285714288e-05, | |
| "loss": 0.0149, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7307692307692308, | |
| "grad_norm": 6.567800521850586, | |
| "learning_rate": 2.357142857142857e-05, | |
| "loss": 0.8362, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.7692307692307692, | |
| "grad_norm": 14.717028617858887, | |
| "learning_rate": 2.2857142857142858e-05, | |
| "loss": 1.7882, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8076923076923077, | |
| "grad_norm": 3.6191389560699463, | |
| "learning_rate": 2.214285714285714e-05, | |
| "loss": 0.113, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8461538461538463, | |
| "grad_norm": 7.102859973907471, | |
| "learning_rate": 2.1428571428571428e-05, | |
| "loss": 0.7773, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.8846153846153846, | |
| "grad_norm": 4.499615669250488, | |
| "learning_rate": 2.0714285714285718e-05, | |
| "loss": 0.2393, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9230769230769231, | |
| "grad_norm": 5.825705528259277, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9615384615384617, | |
| "grad_norm": 4.1611504554748535, | |
| "learning_rate": 1.928571428571429e-05, | |
| "loss": 0.1598, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 17.309432983398438, | |
| "learning_rate": 1.8571428571428572e-05, | |
| "loss": 0.6843, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8431372549019608, | |
| "eval_f1_macro": 0.7110579479000531, | |
| "eval_f1_micro": 0.8431372549019608, | |
| "eval_f1_weighted": 0.8393376489351722, | |
| "eval_loss": 0.4414389729499817, | |
| "eval_precision_macro": 0.7435897435897436, | |
| "eval_precision_micro": 0.8431372549019608, | |
| "eval_precision_weighted": 0.8471593765711413, | |
| "eval_recall_macro": 0.7005005005005005, | |
| "eval_recall_micro": 0.8431372549019608, | |
| "eval_recall_weighted": 0.8431372549019608, | |
| "eval_runtime": 43.3611, | |
| "eval_samples_per_second": 1.176, | |
| "eval_steps_per_second": 0.092, | |
| "step": 52 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 78, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.23173154118697e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |